My Dental Touch
9 month engagement.
+38%
booking conversion
62%
fewer missed calls
4.2x
ROI
“Our front desk finally focuses on patients, not paperwork.”
AI Solutions
Design that drives adoption of the AI you have already built.
Most enterprise AI fails on adoption, not accuracy. We design the interfaces, trust signals and human handoffs that make people willing to rely on an AI system.
HIPAA awareSOC 2 (in progress)ISO 27001 (in progress)5.0 on Clutch
Where organisations get stuck
We shipped an AI feature and almost nobody uses it.
Users do not trust the output so they redo the work manually.
It is unclear when the AI hands off to a person.
Staff see the AI as a threat rather than a tool.
The cost of getting this wrong
Investment with no return
A technically working AI system that nobody adopts delivers zero measurable value.
Shadow manual work
When users distrust output they duplicate it by hand, which adds cost instead of removing it.
Escalation failures
Unclear handoff between AI and staff means customer issues stall in the gap between them.
Change resistance
Poor onboarding turns an operational improvement into an internal political problem.
What we deliver
Agentic UX research and journey mapping
We observe how people actually work and where AI fits into that reality. You get evidence rather than assumptions about adoption barriers.
Conversational and voice interface design
Dialogue design, error recovery, tone and turn taking for chat and voice agents. Designed so the system degrades gracefully instead of failing awkwardly.
Trust, transparency and citation patterns
Interfaces that show confidence, cite sources and make reasoning visible. Users adopt AI they can verify.
Human in the loop and escalation design
Clear handoff moments, approval interfaces and override paths. Staff stay in control and know exactly when to step in.
Onboarding and change adoption design
First run experiences, empty states and progressive disclosure designed for large teams. Adoption is a design problem before it is a training problem.
Design systems for AI products
Reusable components and interaction patterns for AI across your product estate. Consistency reduces the learning cost of every new feature.
How we deliver
Phase 1
Research
User interviews, observation, adoption barrier analysis and current state review.
- Deliverable:
- Research findings and adoption barrier map.
- Timeframe:
- Weeks 1 to 2
Phase 2
Map journeys
End to end journeys including AI and human touchpoints and escalation paths.
- Deliverable:
- Journey maps and interaction model.
- Timeframe:
- Weeks 2 to 3
Phase 3
Prototype
Interactive prototypes of key flows including failure and handoff states.
- Deliverable:
- Clickable prototypes.
- Timeframe:
- Weeks 3 to 6
Phase 4
Test with real users
Usability testing with your actual users and iteration on findings.
- Deliverable:
- Tested designs and test report.
- Timeframe:
- Weeks 6 to 8
Phase 5
Ship and measure
Design handover, build support and adoption measurement setup.
- Deliverable:
- Production design system and adoption metrics.
- Timeframe:
- Weeks 8 to 10
What you get
- Research findings and an adoption barrier map.
- Journey maps covering AI and human touchpoints.
- Interactive prototypes including error and handoff states.
- Usability test results.
- A documented AI design system.
- Adoption measurement instrumentation.
Security, governance and compliance
- Accessibility to WCAG standards.
- Transparent AI disclosure patterns so users know when they are interacting with AI.
- Consent and data use clarity in the interface.
- Escalation to a human always available.
- Research data handled under NDA.
- No client data used to train foundation models.
Integrates with your existing stack
Systems we connect to
FigmaExisting design systemsReact and Next.js front endsiOS and Android appsVoice platformsWhatsAppWeb chatSlackAnalytics platforms
Technology we use
Platforms and frameworks
FigmaReactNext.jsFlutterReact NativeDesign tokensAnalytics and session replay toolingAccessibility testing tools
Proof
Aggregate results from Appnox engagements. Individual outcomes vary by scope and starting point.
How we engage
AI Readiness Assessment
A fixed scope, fixed price assessment that produces a costed, prioritised plan before you commit build budget.
Production Build
A senior delivery team building and shipping the system to production, with agreed scope, milestones and success criteria.
Dedicated Pod
A monthly engineering pod embedded with your team for continuous delivery, iteration and support.
You own all IP. We never train foundation models on your data.
Frequently asked questions
Conventional software is deterministic, so users learn one predictable model. AI is probabilistic, so the interface has to communicate confidence, show sources, allow correction and degrade gracefully when it is wrong. Designing AI like conventional software is the most common cause of low adoption.
Talk to us
Talk to an AI Solutions Architect
Tell us what you are trying to solve. A senior architect, not a salesperson, will reply within one business day with a view on scope, sequence and realistic timelines.
- Senior team, no junior handoff after the pitch.
- Fixed scope and fixed price wherever the scope allows it.
- You own all IP, source code and documentation.